Abstract: Provided are an optimization method, apparatus, device for a wake-up model and a storage medium, which allow for: acquiring a training set and a verification set; performing an iterative training on the wake-up model according to the training set and the verification set; during the iterative training, periodically updating the training set and the verification set according to the wake-up model and a preset corpus database, and continuing performing the iterative training on the wake-up model according to the updated training set and verification set; and outputting the wake-up model when a preset termination condition is reached. The embodiments of the present disclosure, by periodically updating the training set and the verification set according to the wake-up model and the preset corpus database during an iteration, may improve optimization efficiency and effects of the wake-up model, thereby improving stability and adaptability of the wake-up model and avoiding overfitting.

Abstract: An aspect of the present disclosure facilitates processing of natural language (NL) messages. In one embodiment, upon receiving a NL message from a user directed to a chatbot operational in a digital processing system, a data set pertinent for responding to the NL message is formed. An interactive widget that facilitates examination of the formed data set in different views is constructed and sent for display as a response to the NL message. Accordingly, when the interactive widget is displayed (on a display unit), the user is facilitated to examine the data set (pertinent to the NL message) in different views by interacting with the interactive widget.

Abstract: Disclosed are an intelligent voice recognizing method, a voice recognizing device, and an intelligent computing device. According to an embodiment of the present invention, an intelligent voice recognizing method of a voice recognizing device may obtain a microphone detection signal, recognize a user's voice from the microphone detection signal based on a pre-learned speech recognition model, output information related to a result of recognition of the user's voice, and update the speech recognition model based on the output speech recognition result information, easily updating the speech recognition model for speech recognition based on the speech recognition result information which is intuitively shown to the user.

Abstract: The present disclosure relates to a communication method and system for converging a 5th-Generation (5G) communication system for supporting higher data rates beyond a 4th-Generation (4G) system with a technology for Internet of Things (IoT). The present disclosure may be applied to intelligent services based on the 5G communication technology and the IoT-related technology, such as smart home, smart building, smart city, smart car, connected car, health care, digital education, smart retail, security and safety services. Accordingly, the embodiments herein provide a method for managing operations of an electronic device. The method includes transmitting an input signal corrupted by noise to a trained model with a plurality of output states. Further, the method includes dynamically determining an entropy for the plurality of output states of the trained model. Further, the method includes determining whether the entropy exceeds a pre-defined threshold.

Abstract: A method of configuring a laundry course based on speech recognition using artificial intelligence and a device for implementing the same. A washing machine of configuring the laundry course based on the speech recognition includes a speech input unit that receives a speech included with a StainWord or a ClothWord to produce speech data, a communication unit that transmits identification information of speech data and a washing machine to a server and receive course configuring information corresponding to the StainWord or the ClothWord from the server, and a speech guidance unit that outputs a speech guide message that guides a laundry course corresponding to course configuring information, and a control unit that controls a speech input unit, a communication unit, and a speech guidance unit.

Abstract: Systems, methods, and computer-readable storage devices are disclosed for generating smart notes for a meeting based on participant actions and machine learning. One method including: receiving meeting data from a plurality of participant devices participating in an online meeting; continuously generating text data based on the received audio data from each participant device of the plurality of participant devices; iteratively performing the following steps until receiving meeting data for the meeting has ended, the steps including: receiving an indication that a predefined action has occurred on the first participating device; generating a participant segment of the meeting data for at least the first participant device from a first predetermined time before when the predefined action occurred to when the predefined action occurred; determining whether the receiving meeting data of the meeting has ended; and generating a summary of the meeting.

Abstract: A system and method of implementing an intuitive search interface for tactically searching one or more annotated utterance corpora in a machine learning-based dialogue system includes identifying an utterance corpus query for searching one or more annotated utterance corpora of a machine learning-based dialogue system; interpreting the utterance corpus query by translating the utterance corpus query into one or more search expressions recognizable to an utterance sample retrieval program searchably interfacing with the one or more annotated utterance corpora of the machine learning-based dialogue system; retrieving one or more annotated utterance samples from the one or more annotated utterance corpora based on the interpretation of the utterance corpus query; and returning the one or more annotated utterance samples to an intuitive utterance corpus search interface.

Abstract: Disclosed herein are example techniques to identify a voice service to process a voice input. An example implementation may involve a network microphone device (NMD) receiving, via a microphone, voice data indicating a voice input. The NMD may identify, from among multiple voice services registered to a media playback system, a voice service to process the voice input and cause, via a network interface, the identified voice service to process the voice input.

Abstract: Voice-based authentication can include methods, systems, devices, and computer program products for providing user-specific services or access based at least in part on an utterance. In one method, an audio clip having an utterance is obtained. The utterance has an activation trigger portion and a command portion. A first distance between a vector representation of the activation trigger portion and a registered activation trigger vector is determined; and a second distance between a vector representation of the command portion and a registered command vector is determined. Responsive to the first distance satisfying a first distance threshold, and the second distance satisfying a second distance threshold, access is provided to a service associated with a registered user.

Abstract: A method for improving a transcription may include identifying, in the transcription, reliable channel tokens of an utterance of a reliable channel and an unreliable channel token of an utterance of an unreliable channel, and generating, using a machine learning model, a vector embedding for the unreliable channel token and vector embeddings for the reliable channel tokens. The method may further include calculating vector distances between the vector embedding and the vector embeddings, and generating, for the unreliable channel token and using the vector distances, a score corresponding to a reliable channel token. The method may further include determining that the score is within a threshold score, and in response to determining that the score is within the threshold score, replacing, in the transcription, the unreliable channel token with the reliable channel token.

Abstract: Methods and systems for generating conversation models from documents are described herein. A system may receive a document and generate a conversation model that may be deployed by a chatbot or other automated agent (e.g., voice assistant, messenger bot, etc). The chatbot may use the conversation model to engage in a conversation with a user and obtain information from the user to complete the document. The system may generate questions to ask the user based on text in the document that indicates a request for information. Additionally, the system may provide instructions to a user via a chatbot. The instructions may be generated based on text in the document that explains how to fill out the document.

Abstract: Remote generation of executable code for a client application based on natural language commands captured at a client device are described. A natural language command is received at a client device, and natural language data is generated and communicated to a remote service provider system. The service provider system processes the natural language data using natural language processing techniques to recognize one or more actions of the natural language command, and generates executable code to perform the one or more actions of the natural language command by the client application. The executable code is then communicated back to the client device over a network to cause the client application to blindly execute the executable code to perform the one or more actions of the natural language command.

Abstract: Methods, systems and computer program products for facilitating real time conversations based on topic determination are provided. Aspects include receiving one or more user topic profiles. Aspects also include receiving an audio recording of a conversation obtained from one or more audio sensors. Aspects also include converting the audio recording of the conversation to text. Aspects also include determining a topic of the conversation by applying a topic model to the text. Aspects also include determining one or more potentially interested users based on the topic of the conversation and the one or more user topic profiles. Aspects also include notifying the one or more potentially interested users that the conversation is occurring.

Abstract: One or more computing devices, systems, and/or methods for detecting trigger phrases and transmitting electronic messages to devices are provided. For example, audio received via a microphone of a first device may be monitored. Responsive to detecting a first trigger phrase in a first audio segment identified during the monitoring, a first electronic message comprising instructions to activate a microphone function of a second device may be generated and the first electronic message may be transmitted to the second device. Responsive to detecting a second trigger phrase in a second audio segment identified during the monitoring, a second electronic message comprising instructions to activate a microphone function of a third device may be generated and the second electronic message may be transmitted to the third device.

Abstract: A method for generating training data for training a natural language processing system comprises loading, into a computer memory, a computer-readable transcript representing an ordered sequence of one or more dialogue events. The method further comprises acquiring a computer-readable command describing an exemplary ordered subsequence of one or more dialogue events from the computer-readable transcript. The method further comprises re-parametrizing the computer-readable command with an alternative semantic parameter. The method further comprises generating an alternative ordered subsequence of one or more dialogue events based on the re-parametrized computer-readable command. The method further comprises outputting, to a data store, an alternative computer-readable transcript including the alternative ordered subsequence of one or more dialogue events, the alternative computer-readable transcript having a predetermined format usable to train the computerized assistant.

Abstract: An embodiment provides a method, including: receiving, at an audio receiver of an information handling device, user voice input; identifying, using a processor, words included in the user voice input; determining, using the processor, one of the identified words renders ambiguous a command included in the user voice input; accessing, using the processor, context data; disambiguating, using the processor, the command based on the context data; and committing, using the processor, a predetermined action according to the command. Other aspects are described and claimed.

Abstract: The present disclosure provides a method, an apparatus, a device and a system for sign language translation, where a server receives video information sent by a terminal device, and preprocesses the video information to obtain at least one sign language action; the at least one sign language action is input into a sign language model for classification and prediction to obtain a word corresponding to the at least one sign language action; each word is input into a language model to determine whether an intention expression is complete; and each word is sent to the terminal device when the intention expression is complete, so that the terminal device displays each word, thereby realizing the translation of the sign language action into text, enabling the ordinary persons to better understand intentions of the hearing impaired, thus improving efficiency of communications.

Abstract: Methods, apparatus, systems, and computer-readable media are provided for isolating at least one device, from multiple devices in an environment, for being responsive to assistant invocations (e.g., spoken assistant invocations). A process for isolating a device can be initialized in response to a single instance of a spoken utterance, of a user, that is detected by multiple devices. One or more of the multiple devices can be caused to query the user regarding identifying a device to be isolated for receiving subsequent commands. The user can identify the device to be isolated by, for example, describing a unique identifier for the device. Unique identifiers can be generated by each device of the multiple devices and/or by a remote server device. The unique identifiers can be presented graphically and/or audibly to the user, and user interface input. Any device that is not identified can become temporarily unresponsive to certain commands, such as spoken invocation commands.

Abstract: A method for generating a dialogue event in a natural language processing system comprises loading, into a computer memory, a computer-readable seed command describing an ordered sequence of two or more top-level dialogue events. A dialogue event includes a client utterance or a computerized assistant response. The seed command includes one or more sub-commands, each sub-command corresponding to a portion of the ordered sequence of two or more top-level dialogue events, and the focal sub-command of the one or more sub-commands being parametrized by a seed semantic parameter. The method further comprises re-parametrizing the focal sub-command by outputting a plurality of different re-parametrized focal sub-commands wherein, in each re-parametrized focal sub-command, the seed semantic parameter is replaced by one of a plurality of different synthetic semantic parameters.

Abstract: A method and apparatus for translating speech are provided. The method may include: recognizing received to-be-recognized speech of a source language to obtain a recognized text; concatenating the obtained recognized text after a to-be-translated text, to form a concatenated to-be-translated text; inputting the concatenated to-be-translated text into a pre-trained discriminant model to obtain a discrimination result for characterizing whether the concatenated to-be-translated text is to be translated, where the discriminant model is used to characterize a corresponding relationship between a text and a discrimination result corresponding to the text; in response to the positive discrimination result being obtained, translating the concatenated to-be-translated text to obtain a translation result of a target language, and outputting the translation result.